Cited by 380Neural Networks and ApplicationsTheoretical and Computational PhysicsNeural dynamics and brain function

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Associative recall of memory without errors

Kanter, I., Sompolinsky, H.·1987·Physical Review A

Open this paper in CoChat — free account

Abstract

A neural network which is capable of recalling without errors any set of linearly independent patterns is studied. The network is based on a Hamiltonian version of the model of Personnaz et al. The energy of a state of N (\ifmmode\pm\else\textpm\fi{}1) neurons is the square of the Euclidean distance---in phase space---between the state and the linear subspace spanned by the patterns. This energy corresponds to nonlocal updatings of the synapses in the learning mode. Results of the mean-field theory (MFT) of the system as well as computer simulations are presented. The stable and metastable states of the network are studied as a function of ``temperature'' T and \ensuremath{\alpha}=p/N, where p is the number of embedded patterns. The maximum capacity of the network is \ensuremath{\alpha}=1. For all \ensuremath{\alpha} (0\ensuremath{\le}\ensuremath{\alpha}<1) the embedded patterns are not only locally stable but are global minima of the energy. The patterns appear, as metastable states, below a temperature T=${T}_{M}$(\ensuremath{\alpha}). The temperature ${T}_{M}$(\ensuremath{\alpha}) decreases to zero as \ensuremath{\alpha}\ensuremath{\rightarrow}1. The spurious states of the network are studied in detail in the case of random uncorrelated patterns. At finite p, they are identical to the mixture states of Hopfield's model. At finite \ensuremath{\alpha}, a spin-glass phase exists as a metastable state. According to the replica symmetric MFT the spin-glass state becomes degenerate with the patterns at \ensuremath{\alpha}=${\ensuremath{\alpha}}_{g}$=1-2/\ensuremath{\pi} and disappears above it. Possible interpretations of this unusual result are discussed. The average radius of attraction R of the patterns has been determined by computer simulations, for sizes up to N=400. The value of R for 0<\ensuremath{\alpha}<1 depends on the details of the dynamics. Results for both parallel and serial dynamics are presented. In both cases R is unity (the largest distance in phase space by definition) at \ensuremath{\alpha}\ensuremath{\rightarrow}0 and decreases monotonically to zero as \ensuremath{\alpha}\ensuremath{\rightarrow}1. Contrary to the MFT, simulations have not revealed, so far, any singularity in the properties of the spurious states at an intermediate value of \ensuremath{\alpha}.

Integrity signals

Registry

Crossref · 10.1103/physreva.35.380

Cites

13 of 13 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Neural networks and physical systems with emergent collective computational abilities.
Hopfield, J. J. (1982) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.79.8.2554 · Cited by 19,270
Neurons with graded response have collective computational properties like those of two-state neurons.
Hopfield, J. J. (1984) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.81.10.3088 · Cited by 6,918
Solvable Model of a Spin-Glass
Sherrington, D., & Kirkpatrick, S. (1975) · Physical Review Letters · doi:10.1103/physrevlett.35.1792 · Cited by 3,577
Solution of 'Solvable model of a spin glass'
Thouless, D. J., Anderson, P. W., & Palmer, R. G. (1977) · Philosophical magazine · doi:10.1080/14786437708235992 · Cited by 1,305
Spin-glass models of neural networks
Amit, D. J., Gutfreund, H., & Sompolinsky, H. (1985) · Physical Review A · doi:10.1103/physreva.32.1007 · Cited by 1,201
Self-citation
Storing Infinite Numbers of Patterns in a Spin-Glass Model of Neural Networks
Amit, D. J., Gutfreund, H., & Sompolinsky, H. (1985) · Physical Review Letters · doi:10.1103/physrevlett.55.1530 · Cited by 1,098
Self-citation
Order Parameter for Spin-Glasses
Parisi, G. (1983) · Physical Review Letters · doi:10.1103/physrevlett.50.1946 · Cited by 862
Information storage and retrieval in spin-glass like neural networks
Personnaz, L., Guyon, I., & Dreyfus, G. (1985) · Journal de Physique Lettres · doi:10.1051/jphyslet:01985004608035900 · Cited by 329
Collective properties of neural networks: A statistical physics approach
Peretto, P. (1984) · Biological Cybernetics · doi:10.1007/bf00317939 · Cited by 267
Neural networks with nonlinear synapses and a static noise
Sompolinsky, H. (1986) · Physical Review A · doi:10.1103/physreva.34.2571 · Cited by 230
Self-citation

Flagged first, then by citations

Show all 13 references

Research works printed but not linked: 2

1986, Disordered Systems and Biological Organization
A. E. Goles, 1986, Disordered Systems and Biological Organization

Sorted by citations

Cellular neural networks: theory
Chua, L. O., & Yang, L. (1988) · IEEE Transactions on Circuits and Systems · doi:10.1109/31.7600 · Cited by 4,770
Automatic analysis of facial expressions: the state of the art
Pantie, M., & Rothkrantz, L. J. M. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.895976 · Cited by 1,778
The space of interactions in neural network models
Gardner, E. (1988) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/21/1/030 · Cited by 1,061
“The storage capacity for the Hopfield model for random patterns is p = 0.14N, while the pseudo-inverse (Kohonen 1984, Personnaz et al 1985, Kanter and Sompolinsky 1987) stores N linearly independent patterns.”
Method
Optimal storage properties of neural network models
Gardner, E., & Derrida, B. (1988) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/21/1/031 · Cited by 569
Computational Neuroscience of Vision
Rolls, E. T., & Deco, G. (2001) · doi:10.1093/acprof:oso/9780198524885.001.0001 · Cited by 554
The Enhanced Storage Capacity in Neural Networks with Low Activity Level
Tsodyks, M. V., & Feigel’man, M. V. (1988) · Europhysics Letters (EPL) · doi:10.1209/0295-5075/6/2/002 · Cited by 436
Learning algorithms with optimal stability in neural networks
Krauth, W., & Mézard, M. (1987) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/20/11/013 · Cited by 410
Cellular neural networks
Chua, L. O., & Yang, L. (2003) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.1988.15089 · Cited by 406
“Some encouraging if not impressive applications of neural networks have been proposed for various fields such as optimization, linear and nonlinear programming, associative memory, pattern recognition and computer vision[4,5,6,7, 8 ,9,12].”
Background
Maximum Storage Capacity in Neural Networks
Gardner, E. (1987) · Europhysics Letters (EPL) · doi:10.1209/0295-5075/4/4/016 · Cited by 356
Information storage in neural networks with low levels of activity
Amit, D. J., Gutfreund, H., & Sompolinsky, H. (1987) · Physical Review A · doi:10.1103/physreva.35.2293 · Cited by 332
Self-citation
Neural Networks for Pattern Recognition
Kothari, S. C., & Oh, H. (1993) · Advances in computers · doi:10.1016/s0065-2458(08)60404-0 · Cited by 317
Learning of correlated patterns in spin-glass networks by local learning rules
Diederich, S., & Opper, M. (1987) · Physical Review Letters · doi:10.1103/physrevlett.58.949 · Cited by 258
Neuronal models of cognitive functions
Changeux, J., & Dehaene, S. (1989) · Cognition · doi:10.1016/0010-0277(89)90006-1 · Cited by 222
“Mechanism of pattern generation underlying swimming in Tritonia.”
Background
The AdaTron: An Adaptive Perceptron Algorithm
Anlauf, J. K., & Biehl, M. L. (1989) · Europhysics Letters (EPL) · doi:10.1209/0295-5075/10/7/014 · Cited by 207
Neural networks and cellular automata in experimental high energy physics
Denby, B. (1988) · Computer Physics Communications · doi:10.1016/0010-4655(88)90004-5 · Cited by 173
Dense Associative Memory for Pattern Recognition
Krotov, D., & Hopfield, J. J. (2016) · arXiv · doi:10.48550/arxiv.1606.01164
“By modifying the Hamiltonian (1) in a way that removes second order correlations between the stored memories, it is possible [10] to improve the capacity to K = N .”
Method
On the probability that a random ±1-matrix is singular
Kahn, J., Komlós, J., & Szemerédi, E. (1995) · Journal of the American Mathematical Society · doi:10.1090/s0894-0347-1995-1260107-2 · Cited by 158
“geometry (Füredi [4]), threshold logic (Zuev [27]), and associative memories (Kanter-Sompolinsky [11]).”
Background
Associative neural network model for the generation of temporal patterns. Theory and application to central pattern generators
Kleinfeld, D., & Sompolinsky, H. (1988) · Biophysical Journal · doi:10.1016/s0006-3495(88)83041-8 · Cited by 147
Self-citation
Notions of Associative Memory and Sparse Coding
Okada, M. (1996) · Neural Networks · doi:10.1016/s0893-6080(96)00044-5 · Cited by 150
Graded-response neurons and information encodings in autoassociative memories
Treves, A. (1990) · Physical Review A · doi:10.1103/physreva.42.2418 · Cited by 149
Combinatorial interventions inhibit TGFβ-driven epithelial-to-mesenchymal transition and support hybrid cellular phenotypes
Steinway, S. N., Zañudo, J. G. T., Michel, P., Feith, D. J., Loughran, T. P., & Albert, R. (2015) · npj Systems Biology and Applications · doi:10.1038/npjsba.2015.14 · Cited by 129
Asymmetric Hopfield-type networks: Theory and applications
Xu, Z., Guoqing, H., & Kwong, C. P. (1996) · Neural Networks · doi:10.1016/0893-6080(95)00114-x · Cited by 117
Explorations of the mean field theory learning algorithm
Peterson, C., & Hartman, E. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90045-2 · Cited by 121
Epigenetic Landscapes Explain Partially Reprogrammed Cells and Identify Key Reprogramming Genes
Lang, A., Li, H., Collins, J. J., & Mehta, P. (2014) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003734 · Cited by 111
“The model is summarized in Table 1, and Text S1 provides a supplementary overview of attractor neural networks.”
MethodInfluential
Chaos in high-dimensional neural and gene networks
Mestl, T., Lemay, C., & Glass, L. (1996) · Physica D Nonlinear Phenomena · doi:10.1016/0167-2789(96)00086-3 · Cited by 106
A network of oscillators
Abbott, L. F. (1990) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/23/16/028 · Cited by 104
Statistical Mechanics of Generalization
Opper, M., & Kinzel, W. (1996) · Physics of neural networks · doi:10.1007/978-1-4612-0723-8_5 · Cited by 101
The basins of attraction of a new Hopfield learning rule
Storkey, A., & Valabrègue, R. (1999) · Neural Networks · doi:10.1016/s0893-6080(99)00038-6 · Cited by 106
“This learning rulehas a higher capacity than that of the Hebb rule, and still keeps importantfunctionality, such as incrementality and locality, which the pseudo-inverse lacks.”
Background
Neural networks with hierarchically correlated patterns
Gutfreund, H. (1988) · Physical Review A · doi:10.1103/physreva.37.570 · Cited by 92
The theory of neural networks: The Hebb rule and beyond
Sompolinsky, H. (1987) · Lecture notes in physics · doi:10.1007/bfb0057531 · Cited by 92
Self-citation
Statistical mechanics for networks of graded-response neurons
Kühn, R., Bös, S., & van Hemmen, J. L. (1991) · Physical Review A · doi:10.1103/physreva.43.2084 · Cited by 89
Associative memory in an analog iterated-map neural network
Marcus, C. M., Waugh, F. R., & Westervelt, R. M. (1990) · Physical Review A · doi:10.1103/physreva.41.3355 · Cited by 81
Layered neural networks
Domany, E., Kinzel, W., & Meir, R. (1989) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/22/12/013 · Cited by 83
Partial annealing and overfrustration in disordered systems
Доценко, В. С., Franz, S., & Mézard, M. (1994) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/27/7/016 · Cited by 78
Nonlinear dynamics and stability of analog neural networks
Marcus, C. M., Waugh, F. R., & Westervelt, R. M. (1991) · Physica D Nonlinear Phenomena · doi:10.1016/0167-2789(91)90236-3 · Cited by 77
Tuned geometries of hippocampal representations meet the computational demands of social memory
Boyle, L. M., Posani, L., Irfan, S., Siegelbaum, S. A., & Fusi, S. (2024) · Neuron · doi:10.1016/j.neuron.2024.01.021 · Cited by 100
Dreaming neural networks: Forgetting spurious memories and reinforcing pure ones
Fachechi, A., Agliari, E., & Adriano Barra, A. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.01.006 · Cited by 77
Increasing the capacity of a hopfield network without sacrificing functionality
Storkey, A. (1997) · Lecture notes in computer science · doi:10.1007/bfb0020196 · Cited by 76
“This has a capacity of n [ 5 ], but does not have the functionality of the Hebb rule.”
Background
Optimised network for sparsely coded patterns
Vicente, C. J. P., & Amit, D. J. (1989) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/22/5/018 · Cited by 71
The roles of stability and symmetry in the dynamics of neural networks
Krauth, W., Nadal, J., & Mézard, M. (1988) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/21/13/022 · Cited by 71
Temporal Association
Kühn, R., & van Hemmen, J. L. (1991) · Physics of neural networks · doi:10.1007/978-3-642-79814-6_7 · Cited by 67
Exact solution of a layered neural network model
Meir, R., & Domany, E. (1987) · Physical Review Letters · doi:10.1103/physrevlett.59.359 · Cited by 68
Learning and retrieval in attractor neural networks above saturation
Griniasty, M., & Gutfreund, H. (1991) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/24/3/030 · Cited by 61
Incremental learning of complex temporal patterns
Wang, D. L., & Yuwono, B. (1996) · IEEE Transactions on Neural Networks · doi:10.1109/72.548174 · Cited by 62
“Associative memories appear to be able to incorporate more patterns easily so long as the overall number of patterns does not exceed the memory capacity.”
Background
On subspaces spanned by random selections of ±1 vectors
Odlyzko, A. M. (1988) · Journal of Combinatorial Theory Series A · doi:10.1016/0097-3165(88)90046-5 · Cited by 59
Phase transitions in simple learning
Hertz, J., Krogh, A., & Thorbergsson, G. I. (1989) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/22/12/016 · Cited by 58
Storing an extensive number of grey-toned patterns in a neural network using multistate neurons
Rieger, H. (1990) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/23/23/015 · Cited by 54
Training with noise and the storage of correlated patterns in a neural network model
Gardner, E. J., Wallace, D. J., & Stroud, N. (1989) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/22/12/007 · Cited by 56
NDRAM: Nonlinear Dynamic Recurrent Associative Memory for Learning Bipolar and Nonbipolar Correlated Patterns
Chartier, S., & Proulx, R. (2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2005.852861 · Cited by 55
“It is noted that these 12 patterns represent a memory load of 34%, which is greater than the Hopfield network capacity (around 15% [3]).”
BackgroundMethodInfluential
Statistical mechanics for networks of analog neurons
Kühn, R. (2008) · Springer eBooks · doi:10.1007/3540532676_38 · Cited by 53
Learning times of neural networks: Exact solution for a PERCEPTRON algorithm
Opper, M. (1988) · Physical Review A · doi:10.1103/physreva.38.3824 · Cited by 52
Learning in Neural Networks: Solvable Dynamics
Opper, M. (1989) · Europhysics Letters (EPL) · doi:10.1209/0295-5075/8/4/015 · Cited by 47
Bayesian retrieval in associative memories with storage errors
Sommer, F. T., & Dayan, P. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/72.701183 · Cited by 40
“Another modification, which is already prescribed by more expensive storage strategies such as pseudoinverse learning [36] to restrict the search space to the vicinity of the initial pattern is to add a positive offset in all diagonal weights .”
Method
Fully Connected Neural Networks with Self-Control of Noise Levels
Lewenstein, M., & Nowak, A. K. (1989) · Physical Review Letters · doi:10.1103/physrevlett.62.225 · Cited by 41
Glauber dynamics of the Little-Hopfield model
Rieger, H., Schreckenberg, M., & Zittartz, J. (1988) · The European Physical Journal B · doi:10.1007/bf01314534 · Cited by 40
High capacity recurrent associative memories
Davey, N., Hunt, S. P., & Adams, R. G. (2004) · Neurocomputing · doi:10.1016/j.neucom.2004.02.007 · Cited by 41
Collective Phenomena in Neural Networks
van Hemmen, J. L., & Kühn, R. (1995) · Physics of neural networks · doi:10.1007/978-3-642-79814-6_1 · Cited by 44
When shared concept cells support associations: Theory of overlapping memory engrams
Gastaldi, C., Schwalger, T., Falco, E. D., Quiroga, R. Q., & Wulfram Gerstner, B. (2021) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1009691 · Cited by 38
Feedback associative memory based on a new hybrid model of generalized regression and self-feedback neural networks
Amiri, M., Davande, H., Sadeghian, A., & Chartier, S. (2010) · Neural Networks · doi:10.1016/j.neunet.2010.05.005 · Cited by 39
The phase space of interactions in neural networks with definite symmetry
Gardner, E., Gutfreund, H., & Yekutieli, I. (1989) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/22/12/005 · Cited by 38
“pseudo-inverse rule (Kohonen 1984), which has been applied to these models by Personnaz er a1 (1985) and studied analytically by Kanter and Sompolinsky (1987).”
Method
Recognition of topological features of graphs and images in neural networks
Kree, R., & Zippelius, A. (1988) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/21/16/006 · Cited by 39
Statistical mechanics for neural networks with continuous-time dynamics
Kühn, R., & Bös, S. (1993) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/26/4/012 · Cited by 38
Analog Photonics Computing for Information Processing, Inference, and Optimization
Stroev, N., & Berloff, N. G. (2023) · Advanced Quantum Technologies · doi:10.1002/qute.202300055 · Cited by 42
Bidirectional associative memories
Acevedo, E., Yáñez-Márquéz, C., & Acevedo, A. (2013) · ACM Computing Surveys · doi:10.1145/2431211.2431217 · Cited by 36
Storage capacity of non-monotonic neurons
CRESPI, B. (1999) · Neural Networks · doi:10.1016/s0893-6080(99)00074-x · Cited by 37
“MR the system completely loses its retrieval capability (Abbott & Arian, 1987; Gardner, 1987; Kanter & Sompolinsky, 1987).”
Background
Designing asymmetric neural networks with associative memory
Zhao, H. W. (2004) · Physical Review E · doi:10.1103/physreve.70.066137 · Cited by 38
Associative memory based on parametrically coupled chaotic elements
Ishii, S., & Sato, M.-A. (1998) · Physica D Nonlinear Phenomena · doi:10.1016/s0167-2789(98)00155-9 · Cited by 37
“If we could make the activation rate low so that the retrieval state had a large correlation with the target memory but a small correlation with non-target memories, the memory capacity would increase, like that achieved by the generalized-inverse matrix method [20, 19].”
Method
Regularization, early-stopping and dreaming: A Hopfield-like setup to address generalization and overfitting
Agliari, E., Alemanno, F., Aquaro, M., & Fachechi, A. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106389 · Cited by 42
Dreaming neural networks: rigorous results
Agliari, E., Alemanno, F., Barra, A., & Fachechi, A. (2019) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/ab371d · Cited by 37
“…entire sleep session) to live solely within a -quite large-retrieval region, surrounded by ergodicity: noticing that at this ﬁnal stage of sleeping the network approached the Kanter-Sompolinsky model [43], it shines why these Authors called their model associative recall of memory without errors .”
MethodResultInfluential
Statistical mechanics of Hopfield-like neural networks with modified interactions
Доценко, В. С., YARUNIN, N. D., & Dorotheyev, E. A. (1991) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/24/10/026 · Cited by 36
Recognition with self-control in neural networks
Lewenstein, M., & Nowak, A. K. (1989) · Physical Review A · doi:10.1103/physreva.40.4652 · Cited by 34
Layered feed-forward neural network with exactly soluble dynamics
Meir, R., & Domany, E. (1988) · Physical Review A · doi:10.1103/physreva.37.608 · Cited by 35
A Sequential Dynamic Heteroassociative Memory for Multistep Pattern Recognition and One-to-Many Association
Chartier, S., & Boukadoum, M. (2006) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2005.860855 · Cited by 32
“Thus, if we want the network to respond within a reasonable time, the number of stored patterns should be less than half the network dimension [13] , [19].”
Background
Learning grey-toned patterns in neural networks
Mertens, S., Kohler, H. M., & Bös, S. (1991) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/24/20/023 · Cited by 33
Analog neural networks with local competition. I. Dynamics and stability
Waugh, F. R., & Westervelt, R. M. (1993) · Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics · doi:10.1103/physreve.47.4524 · Cited by 32
Universality in the space of interactions for network models
Abbott, L. F., & Kepler, T. B. (1989) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/22/12/008 · Cited by 32
High capacity, small world associative memory models
Davey, N., Calcraft, L., & Adams, R. (2006) · Connection Science · doi:10.1080/09540090600639339 · Cited by 31
“In our implementation we have slightly adapted the method of Kanter and Sompolinsky (1987) in the calculation of R.”
BackgroundMethod
A simple model for Behavioral Time Scale Synaptic Plasticity (BTSP) provides content addressable memory with binary synapses and one-shot learning
Wu, Y., & Maass, W. (2025) · Nature Communications · doi:10.1038/s41467-024-55563-6 · Cited by 36
A Novel Continuous-Valued Quaternionic Hopfield Neural Network
Valle, M. E. (2014) · Brazilian Conference on Intelligent Systems · doi:10.1109/bracis.2014.28 · Cited by 30
“The paper finishes with concluding remarks in Section V.”
Background
Facial expressions recognition using discrete Hopfield neural networks
Yoneyama, M., Ohtake, A., Iwano, Y., & Shirai, K. (2002) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.1997.647398 · Cited by 30
High capacity associative memories and connection constraints
Davey, N., & Adams, R. (2004) · Connection Science · doi:10.1080/09540090310001659981 · Cited by 30
“As is pointed out in Kanter and Sompolinsky (1987), for finite size associative memories, another factor needs to be considered.”
Background
Self-evolution neural model
Shuai, J., Chen, Z., Liu, R., & Wu, B. (1996) · Physics Letters A · doi:10.1016/0375-9601(96)00594-4 · Cited by 30
Generalization ability of perceptrons with continuous outputs
Bös, S., Kinzel, W., & Opper, M. (1993) · Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics · doi:10.1103/physreve.47.1384 · Cited by 30
PSEUDO-RELAXATION LEARNING ALGORITHM FOR COMPLEX-VALUED ASSOCIATIVE MEMORY
Kobayashi, M. (2008) · International Journal of Neural Systems · doi:10.1142/s0129065708001452 · Cited by 29
Reconfigurable Neuromorphic Computing System with Memristor-Based Synapse Design
Liu, B., Chen, Y., Wysocki, B. T., & Huang, T. (2013) · Neural Processing Letters · doi:10.1007/s11063-013-9315-8 · Cited by 30
“Based on previous work on associative recall [15], the capacity limits of Hopfield network is ∼15 %, or about two patterns in a system of 12 neurons.”
Background
Characterizing cancer subtypes as attractors of Hopfield networks
Maetschke, S., & Ragan, M. A. (2014) · Bioinformatics · doi:10.1093/bioinformatics/btt773 · Cited by 29
“We evaluated high-capacity learning rules by Kanter and Sompolinsky (1987) and Storkey and Valabregue (1999) that allow storage of n linearly independent patterns.”
Method
Outperforming RBM Feature-Extraction Capabilities by “Dreaming” Mechanism
Fachechi, A., Adriano Barra, A., Agliari, E., & Alemanno, F. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3182882 · Cited by 29
“…effective to analyze retrieval capabilities of associative memory models even beyond the paradigmatic HNN; for instance, Kanter and Sompolinski [19] considered a model where couplings among neurons are revised, and they showed that the resulting storage limit α c (i.e., the critical ratio of…”
Background
Hierarchical associative networks
Cortes, C., Krogh, A., & Hertz, J. (1987) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/20/13/044 · Cited by 29
Associative memory of structured knowledge
Steinberg, J., & Sompolinsky, H. (2022) · Scientific Reports · doi:10.1038/s41598-022-25708-y · Cited by 30
“We use this relation to determine lc(α) as a function of L0/L using the value of mmin(α) obtained for a Pseudoinverse model with random binary patterns as memories [2].”
InfluentialSelf-citation
On the effective initialisation for restricted Boltzmann machines via duality with Hopfield model
Leonelli, F. E., Agliari, E., Albanese, L., & Adriano Barra, A. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.06.017 · Cited by 30
Emergent properties of collective gene-expression patterns in multicellular systems
Smart, M., & Zilman, A. (2023) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2023.101247 · Cited by 27
“non-orthogonal), we use the projection rule (34, 35) for pattern storage as in (29).”
BackgroundMethod
Spin glass states of the anti-Hopfield model
Nokura, K. (1998) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/31/37/007 · Cited by 27
The Magnitude of the Diagonal Elements in Neural Networks
Wilde, P. D. (1997) · Neural Networks · doi:10.1016/s0893-6080(96)00094-9 · Cited by 26
Computational capabilities of restricted two-layered perceptrons
Priel, A., Blatt, M., Grossman, T., Domany, E., & Kanter, I. (1994) · Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics · doi:10.1103/physreve.50.577 · Cited by 26
Self-citation
Basins of attraction near the critical storage capacity for neural networks with constant stabilities
Opper, M., Kleinz, J., Köhler, H., & Kinzel, W. (1989) · Journal of Physics A Mathematical and General · doi:10.1088/0305-4470/22/9/010 · Cited by 26
The Circuit Realization of a Neuromorphic Computing System with Memristor-Based Synapse Design
Liu, B., Chen, Y., Wysocki, B. T., & Huang, T. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-34475-6_43 · Cited by 25
BAM Learning of Nonlinearly Separable Tasks by Using an Asymmetrical Output Function and Reinforcement Learning
Chartier, S., Boukadoum, M., & Amiri, M. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2009.2023120 · Cited by 25
“A typical BAM with units can associate up to patterns [23].”
Supervised perceptron learning vs unsupervised Hebbian unlearning: Approaching optimal memory retrieval in Hopfield-like networks
Benedetti, M., Ventura, E., Marinari, E., Ruocco, G., & Zamponi, F. (2022) · The Journal of Chemical Physics · doi:10.1063/5.0084219 · Cited by 22
“[10] tends to the pseudo-inverse connectivity matrix [29], poorer generalization performances, i.e. smaller basins of attraction, should be expected [8].”
Background
Influence of random topology in artificial neural networks: A survey
Kaviani, S., & Sohn, I. (2020) · ICT Express · doi:10.1016/j.icte.2020.01.002 · Cited by 27
Information maximization in face processing
Bartlett, M. S. (2007) · Neurocomputing · doi:10.1016/j.neucom.2006.02.025 · Cited by 23
“In this model, a decorrelation step was necessary in order to encode highly similar patterns in a Hopfield attractor network [35].”

Authors: Kanter, I., & Sompolinsky, H.
Affiliations: Bar-Ilan University (IL)
ORCID: Kanter, I.
Sompolinsky, H.
Venue: Physical Review A
Publisher: American Physical Society (APS)
Published: 1987-01-01
Volume: 35
Issue: 1
Pages: 380-392
ISSN: 0556-2791 (ISSN-L)
DOI: 10.1103/physreva.35.380
OpenAlex: W2029182425
Cited by: 379
References: 13
Citations by year: 2026: 9 · 2025: 11 · 2024: 13 · 2023: 6 · 2022: 10 · 2021: 9 · 2020: 6 · 2019: 6 · 2018: 1 · 2017: 4 · 2016: 4 · 2015: 2 · 2014: 7 · 2013: 6 · 2012: 6
FWCI: 30.30
Type: journal article
Language: en
Open access: closed
Licence: link.aps.org/licenses/aps-default-license (vor)
Locations: Physical Review A (publishedVersion)
PubMed (publishedVersion)
Topics: Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
Physical Sciences › Physics and Astronomy › Condensed Matter Physics › Theoretical and Computational Physics
Life Sciences › Neuroscience › Cognitive Neuroscience › Neural dynamics and brain function
Keywords: associative memory, mean-field theory, metastable states, spin glass phase, spurious states, Hopfield neural network, capacity

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Associative recall of memory without errors

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Citations

Cites

Cited by

Related

Metadata

Record

About these checks